Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     penned
    -0.07
     χαρα
    -0.06
     clown
    -0.06
    ीकरण
    -0.06
    赖
    -0.06
    efe
    -0.06
     разд
    -0.06
    ọn
    -0.06
    coil
    -0.06
     robe
    -0.05
    POSITIVE LOGITS
     SpaceX
    0.07
    icmp
    0.07
     hol
    0.06
     moll
    0.06
    icultural
    0.06
     expressive
    0.06
    azen
    0.06
     LIS
    0.06
    _lhs
    0.06
    EMPL
    0.06
    Act Density 0.005%

    No Known Activations